Grok Imagine Video 1.5 video
xai/grok-imagine-video-1.5 · family grok · in: text, image, audio, pdf → out: video · price provider-declared (via models.dev). Capabilities: text image audio pdf.
This is a video model — providers price it per second / clip, not per token, so models.dev carries no token price (fields read “—”). See xAI’s docs for per-unit rates.
- Provider
- xAI (
xai) - Kind
- video (outputs video)
- Context
- 1,024 tokens
- Max output
- 0 tokens
- Capabilities
- text image audio pdf
Same model, other providers
“Grok Imagine Video 1.5” is offered by 2 providers — priced per unit; see each provider for rates.
| Provider | Input | Output | Context |
|---|---|---|---|
| xAI (this) | — | — | 1k |
| Vercel AI Gateway | — | — | 0 |
Call it
jishie indexes & prices models; it does not proxy inference.
Video generation — call xAI’s video API with model id grok-imagine-video-1.5. Endpoints vary by provider; see their docs.
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):